On Neural Network Algorithms for Solving Non- Linear Problems: Optimizations and Non-linear programming par Sadq, Gulnar, Younis Al-Bayati, Abbas, Abdulla Sulaiman, Naj: Like New Paperback (2012)

A propos de cet article

Like New.

N� de r�f. du vendeur D7F9-6-M-3846580805-6

Contacter le vendeur

Signaler cet article

D�tails bibliographiques

Titre: On Neural Network Algorithms for Solving Non- Linear Problems: Optimizations and Non-linear programming
�diteur: LAP LAMBERT Academic Publishing
Date de parution: 2012
Langue: anglais
ISBN � 10 chiffres: 3846580805
ISBN � 13 chiffres: 9783846580806
Reliure: Paperback
�tat de l'article: Like New
Type de livre: book

A propos de ce titre

Synopsis

First we describe, analyze and present the theoretical derivations and the source codes for several (modified and well-known) non-linear Neural Network algorithms based on the unconstrained optimization theory and applied to supervised training networks. In addition to the indication of the relative efficiency of these algorithms in an application, we analyze their main characteristics and present the MATLAB source codes. Algorithms of this part depend on some modified variable metric updates and for the purpose of comparison, we illustrate the default values specification for each algorithm, presenting a simple non-linear test problem. Further more in this thesis we also emphasized on the conjugate gradient (CG) algorithms, which are usually used for solving nonlinear test functions and are combined with the modified back propagation (BP) algorithm yielding few new fast training multilayer Neural Network algorithms. This study deals with the determination of new search directions by exploiting the information calculated by gradient descent as well as the previous search directions.

Pr�sentation de l'�diteur

First we describe, analyze and present the theoretical derivations and the source codes for several (modified and well-known) non-linear Neural Network algorithms based on the unconstrained optimization theory and applied to supervised training networks. In addition to the indication of the relative efficiency of these algorithms in an application, we analyze their main characteristics and present the MATLAB source codes. Algorithms of this part depend on some modified variable metric updates and for the purpose of comparison, we illustrate the default values specification for each algorithm, presenting a simple non-linear test problem. Further more in this thesis we also emphasized on the conjugate gradient (CG) algorithms, which are usually used for solving nonlinear test functions and are combined with the modified back propagation (BP) algorithm yielding few new fast training multilayer Neural Network algorithms. This study deals with the determination of new search directions by exploiting the information calculated by gradient descent as well as the previous search directions.

Les informations fournies dans la section � A propos du livre � peuvent faire r�f�rence � une autre �dition de ce titre.